About DIAG

Mammography

When mammography screening for breast cancer started in The Netherlands in 1989, the national reference center was established in Nijmegen. Nico Karssemeijer, a post-doc at Radboud University Medical Center, realized that computer analysis of mammograms was going to be a key area within medical image analysis, especially when digital screening would become a reality. He published his first paper on the automatic detection of abnormalities in mammograms in 1992. Karssemeijer soon established one of the leading groups in the emerging field of computer-aided detection and diagnosis (CAD). He set up a long collaboration with the California based company R2 Technology, which developed the first FDA approved CAD product for detecting breast cancer in mammograms and still market leader in the field of mammography CAD. The core technology for this product is based on Karssemeijer's method of stellate distortion detection.

Mammography CAD remains an active research area within our group. Research has expanded into breast density estimation, together with Matakina Ltd (Wellington, New Zealand), a startup co-founded by Karssemeijer, and the design of computer-aided detection and diagnosis systems for other modalities, such as 3D ultrasound, MRI, and tomosynthesis.

Prostate image analysis

Henkjan Huisman, who obtained his PhD in 1998 on ultrasound analysis joined Nico Karssemeijer to expand the field of research to breast and prostate MRI. His first publication with Jelle Barentsz on the topic appeared in 1999. Nijmegen is a worldwide leading center for prostate cancer imaging, and DIAG therefore pioneered the development of prostate CAD and decision support systems. DIAG software is used on a daily basis in clinical practice in the radiology department.

Formation of DIAG and a focus on chest

In 2010 the group was expanded because Bram van Ginneken came from University Medical Center Utrecht and joined Nico Karssemeijer. In January 2010, the name Diagnostic Image Analysis Group, DIAG for short, was adopted. In 2011 and 2012, Nico Karssemeijer and Bram van Ginneken were appointed full professor at Radboud University. During these years, the group grew quickly to over 20 full time researchers.

Bram van Ginneken had performed his PhD research on the automatic detection of tuberculosis in chest radiographs at the Image Sciences Institute in Utrecht, The Netherlands from 1997 to 2001. This work continues within DIAG to date, co-funded by the Dutch company Delft Imaging Systems under the name CAD4TB. The automatic system that analyzes chest radiographs for signs of tuberculosis is now operational in ten African and Asian countries.

In Utrecht, Bram van Ginneken started to work on the analysis of chest CT scans in 2003, and together with Mathias Prokop, now head of the Department of Radiology and Nuclear Medicine at Radboud University Medical Centre, began to develop a wide range of techniques and applied these to the data of the NELSON lung screening trial for which Utrecht was one of the centers. Eva van Rikxoort was one of the PhD students who graduated in the Utrecht chest CT group of Van Ginneken and Prokop, and after a postdoc at UCLA she joined DIAG in 2011. In the same year, the chest radiologist Cornelia Schaefer-Prokop also joined DIAG making chest CT a key focus within the group.

Retinal image analysis

Another activity that Bram van Ginneken started in Utrecht and continued in Nijmegen was analysis of retinal images. Clarisa Sanchez joined Bram van Ginneken in Utrecht as a postdoc and went with him to Nijmegen where she is now a faculty member, leading the research on image analysis of ophthalmological images. DIAG is closely collaborating with Radboudumc's Department of Ophthalmology in this area and a first joint paper was published in 2013.

More topics, more people

DIAG has also expanded its activities to neuro image analysis with MRI and 4D computed tomography, and has more recently started several projects in the area of digital pathology.

In 2015, the group has grown to 8 faculty members, 5 post-docs, 4 scientific programmers, and 28 PhD students. DIAG is a very diverse and international group, our 45 researchers originally come from 12 different countries.

Strategic collaboration with Fraunhofer MEVIS

Bremen-based Fraunhofer MEVIS and DIAG have been successfully collaborating as partners in research projects in the area of breast imaging since the mid-nineties. This cooperation already started in the mid-nineties, long before MEVIS became part of the Fraunhofer-Gesellschaft. Researchers of FME and DIAG were the driving force in three success-ful EU consortia. In two of them (SCREEN and SCREEN-TRIAL), a reading environment for breast cancer screening was developed, which led to a worldwide leading market position of MEVIS spin-out company MeVis Medical Solutions AG.

In 2010 this collaboration was taken to a next level and DIAG is now part of the Fraunhofer MEVIS family tree. There is a continuous exchange of personnel between the two groups. Currently two faculty members of DIAG hold part-time positions at Fraunhofer MEVIS (Bram van Ginneken and Eva van Rikxoort) and several others have done so in the past.

Two large EU projects on breast imaging (ASSURE and VPH-PRISM, coordinated by DIAG and Fraunhofer MEVIS, respectively) started in 2012 and 2013. In the area of chest CT, Fraunhofer MEVIS and DIAG are jointly collaborating with MeVis Medical Solutions. In 2014 Veolity, software to efficiently read screening chest CT scans, was introduced.

DIAGTechnologies and CIRRUS

DIAGTechnologies was established in 2012 as a division of DIAG with the purpose of providing an organization that can develop, maintain, and distribute software for analysis of medical images in a quality controlled certified environment. As of 2013, DIAGTechnologies is fully compliant with MDD Annex II and ISO 13485. The first product released by DIAGTechnologies is ProCAD, an optimized reading environment for multi-parametric prostate MRI studies. ProCAD is CE marked for distribution within Europe since May 2013 and TGA marked for distribution in Australia since November 2013. In March 2014, the second product of DIAGTechnologies, CAD4TB, was CE marked.

In 2010 DIAG adopted MeVisLab as software environment to build applications. To achieve a consistent user interface for all our applications with the look and feel of a modern radiological workstation, we have built CIRRUS. Most of the applications developed by DIAG researchers use CIRRUS.

Industry collaborations

With its focus on creating clinical applications of its algorithmic solution for medical image analysis, DIAG is closely collaborating with a wide range of companies. The following companies directly fund research carried out at DIAG, or have done so in the recent past:

  • Toshiba Medical Systems Corporation (Japan) is working with DIAG on 4D CT image analysis and evaluation of novel ultrasound technologies. CT topics include protocol optimization, dose reduction, subtraction imaging and an optimized workup for stroke suspects. There is also an active collaboration with the ultrasound division of Toshiba. Topics include quantitative ultrasound and CT/MR guided biopsies.
  • Mevis Medical Solutions (MMS) (formerly MeVis Technology AG) was founded in 1997 as an independent spin-off of MeVis Research (today Fraunhofer MEVIS) to act as a commercial partner and to facilitate the transfer of research results into marketable products. DIAG works with MMS in the area of lung CT screening and breast image analysis.
  • Delft Imaging Systems (DIS) develops diagnostic imaging equipment and e-health software. DIS is the only imaging company worldwide to invest in x-ray solutions that assist the medical community in the fight against tuberculosis. DIAG and DIS have developed CAD4TB, CE marked software for the automated interpretation of chest radiographs.
  • Riverain Technologies from Dayton, Ohio, develops proprietary pattern recognition and machine learning technologies to process and analyze chest radiographs. DIAG has developed algorithms for Riverain and is currently carrying out observer studies with Riverain's software to investigate the effect of using bone suppression, temporal analysis and nodule detection on clinical practice.
  • Matakina is a start-up company co-founded by Nico Karssemeijer that is based in the UK and New Zealand and which develops software for mammographic image analysis. Matakina’s first product is Volpara, an automatic software system that gives a breast density score based on an estimate of the volume of dense tissue in the breast. Matakina is funding DIAG research towards improvements of breast density estimation methods.
  • MedQIA is an imaging contract research organization based in Los Angeles that specializes in quantitative image analysis for clinical trials. DIAG is working with MedQIA in the area of lung CT image analysis.
  • QView Medical, Los Altos, California was co-founded by Nico Karssemeijer and Henkjan Huisman and is working on 3D breast ultrasound image analysis. Together with DIAG new computer-aided detection algorithms are developed.

Spin-off companies

In 2014, two spin-off companies were established by DIAG members. Nico Karssemeijer founded ScreenPoint, focusing on solutions for computerized interpretation of mammograms and digital breast tomosynthesis. Eva van Rikxoort and Bram van Ginneken started Thirona, a company that provides tools and services for medical image analysis and imaging quantification. Several alumni of DIAG work in these new companies.